0
我试着用不同的超参数重复运行tensorflow
深度学习程序。Tensorflow:我如何反复运行tensorflow作业?
for i in range(10):
my_learner = DQNLearner()
my_learner.build_network()
my_learner.run()
class DQNLearner():
def build_network(self):
W1 = tf.get_variable(
"W1",
shape=[self.input_size, h_size],
initializer=tf.contrib.layers.xavier_initializer()
)
b1 = tf.Variable(tf.random_normal([h_size]))
L1 = tf.nn.relu(tf.matmul(self._X, W1) + b1)
L1 = tf.nn.dropout(L1, keep_prob=self.keep_prob)
W2 = tf.get_variable(
"W2",
shape=[h_size, h_size],
initializer=tf.contrib.layers.xavier_initializer()
)
b2 = tf.Variable(tf.random_normal([h_size]))
L2 = tf.nn.relu(tf.matmul(L1, W2) + b2)
L2 = tf.nn.dropout(L2, keep_prob=self.keep_prob)
.
.
.
.
.
它在第一次循环中效果很好。但在第二个循环中,它是这样发生的:
ValueError: Variable W1 already exists, disallowed. Did you mean to set reuse=True in VarScope? Originally defined at:
我该如何解决它?